Machine Learning Engineer, E-Commerce Governance - USDS

$137,750 - $237,500/Yr

Tiktok - Seattle, WA

Full-time - Mid Level

Seattle, WA

Computing Infrastructure Providers, Data Processing, Web Hosting, and Related Services

About the position

TikTok is the leading destination for short-form mobile video, and our mission is to inspire creativity and bring joy. U.S. Data Security (USDS) is a subsidiary of TikTok in the U.S., created to enhance focus and governance on our data protection policies and content assurance protocols to ensure the safety of U.S. users. Our commitment is to provide oversight and protection of the TikTok platform and U.S. user data, allowing millions of Americans to continue using TikTok for learning, earning, self-expression, and entertainment. The teams within USDS that deliver on this commitment span across Trust & Safety, Security & Privacy, Engineering, User & Product Ops, Corporate Functions, and more. The Governance and Experience Algorithm team, established in September 2020, is dedicated to supporting various businesses with advanced AI technology. This includes combating risks and violations in e-commerce scenarios and building a healthy e-commerce ecosystem while improving platform service capabilities. As a Machine Learning Engineer in this team, you will be responsible for identifying algorithms for risk, violation, and low-quality issues in e-commerce scenarios, including products, shopping cart short videos, and live streaming with products. You will also mine and identify algorithms to detect fraudulent behaviors and identify risky, violated, or low-quality merchants and creators. Your role will involve optimizing algorithms for large-scale brand libraries, products, and content deduplication/clustering, as well as data construction, instruction fine-tuning, and alignment for large models in the e-commerce domain. You will explore reinforcement learning and operational research algorithms to improve audit quality and efficiency. This position requires a hybrid work schedule, with employees expected to work in the office three days a week, or as directed by their manager/department, with regular reviews of the hybrid work model.

Responsibilities

• Identify algorithms for risk, violation, and low-quality issues in e-commerce scenarios such as products, shopping cart short videos, and live streaming with products.
• Mine and identify algorithms to detect fraudulent behaviors and identify risky, violated, or low-quality merchants and creators.
• Optimize algorithms for large-scale brand libraries, products, and content deduplication/clustering.
• Conduct data construction, instruction fine-tuning, and alignment for large models in the e-commerce domain to optimize effects.
• Explore reinforcement learning and operational research algorithms to improve audit quality and efficiency.
• Optimize various basic algorithms such as NLP, vision, multimodal, search, graph, and LLM to support governance business.
• Streamline the optimization and iteration process for computer vision models in e-commerce settings.
• Optimize video classification, multimodal content mining, and understanding of e-commerce short videos and live broadcasts.
• Optimize risk identification models related to text content in e-commerce scenarios.
• Optimize risk mining algorithms for comments, reports, and other public opinion content related to products/short videos/live broadcasts.
• Research large-scale multimodal algorithms and their implementation in e-commerce scenarios.
• Extract extensive data from various entities to support business scenarios like content understanding and community mining.

Requirements

• Bachelor's degree or above in computer science or related field.
• Solid coding skills, ability to develop in a Linux environment, proficient in Python, Go, or C++.
• Solid foundation in data structures/algorithms, proficient in machine learning/deep learning theory, and rich practical experience.
• Familiar with 1-2 areas in natural language processing, computer vision, multimodal, graph algorithms, search algorithms, text/data mining, and LLM.
• Excellent analytical and problem-solving skills, passionate about challenging problems.
• Good team spirit and strong communication skills.

Nice-to-haves

• Experience in platform governance/audit/risk control/content security or overseas internet/e-commerce business.

Benefits

• 100% premium coverage for employee medical insurance, approximately 75% premium coverage for dependents.
• Health Savings Account (HSA) with a company match.
• Dental, Vision, Short/Long term Disability, Basic Life, Voluntary Life and AD&D insurance plans.
• Flexible Spending Account (FSA) Options like Health Care, Limited Purpose and Dependent Care.
• 10 paid holidays per year plus 17 days of Paid Personal Time Off (PPTO) and 10 paid sick days per year.
• 12 weeks of paid Parental leave and 8 weeks of paid Supplemental Disability.
• Mental and emotional health benefits through EAP and Lyra.
• 401K company match, gym and cellphone service reimbursements.